© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88819
    Prev
    Next
    INDEX
    Explanations

    Numbers, programming, and science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è§ī
    -0.29
    fil
    -0.28
    ãİľ
    -0.26
    west
    -0.26
    ç®±
    -0.24
    creds
    -0.24
    FFFF
    -0.23
    .VideoCapture
    -0.23
    ä»Ģä¹Īéĥ½
    -0.23
    èĥ¶
    -0.23
    POSITIVE LOGITS
     Erl
    0.26
    å®ĺæĸ¹å¾®åįļ
    0.26
    çļĦä¸Ģç§į
    0.26
     goose
    0.25
     ning
    0.25
     nog
    0.25
    .svg
    0.25
    ог
    0.24
    IRC
    0.23
    oksen
    0.23
    Activations Density 0.004%

    No Known Activations